{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FCGTOC574WSNQO7A6MFY7PLTTB","short_pith_number":"pith:FCGTOC57","schema_version":"1.0","canonical_sha256":"288d370bbfe5a4d83be0f30b8fbd73984d70ef1da395dbf798adf7364fda121b","source":{"kind":"arxiv","id":"2310.11011","version":2},"attestation_state":"computed","paper":{"title":"From Identifiable Causal Representations to Controllable Counterfactual Generation: A Survey on Causal Generative Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aneesh Komanduri, Feng Chen, Xintao Wu, Yongkai Wu","submitted_at":"2023-10-17T05:45:32Z","abstract_excerpt":"Deep generative models have shown tremendous capability in data density estimation and data generation from finite samples. While these models have shown impressive performance by learning correlations among features in the data, some fundamental shortcomings are their lack of explainability, tendency to induce spurious correlations, and poor out-of-distribution extrapolation. To remedy such challenges, recent work has proposed a shift toward causal generative models. Causal models offer several beneficial properties to deep generative models, such as distribution shift robustness, fairness, a"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2310.11011","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-17T05:45:32Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"751261f71c50a16c39413ba1ef96053b790162b1a44e2b9202a5f1d47e09b9f2","abstract_canon_sha256":"a30da1cbad480ea40146008daa98460ba503c38db87647658d633a851758c6ba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:22:21.567766Z","signature_b64":"eYW2YwLlscjcpGXepG/4Kuf5THOdBWR+6dMr/WdU9mb/NBCV2HNKhRGttuVSA+b5cydvBH0V5W+4iBWlpY6EDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"288d370bbfe5a4d83be0f30b8fbd73984d70ef1da395dbf798adf7364fda121b","last_reissued_at":"2026-07-05T08:22:21.567286Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:22:21.567286Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Identifiable Causal Representations to Controllable Counterfactual Generation: A Survey on Causal Generative Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aneesh Komanduri, Feng Chen, Xintao Wu, Yongkai Wu","submitted_at":"2023-10-17T05:45:32Z","abstract_excerpt":"Deep generative models have shown tremendous capability in data density estimation and data generation from finite samples. While these models have shown impressive performance by learning correlations among features in the data, some fundamental shortcomings are their lack of explainability, tendency to induce spurious correlations, and poor out-of-distribution extrapolation. To remedy such challenges, recent work has proposed a shift toward causal generative models. Causal models offer several beneficial properties to deep generative models, such as distribution shift robustness, fairness, a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.11011","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2310.11011/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2310.11011","created_at":"2026-07-05T08:22:21.567349+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.11011v2","created_at":"2026-07-05T08:22:21.567349+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.11011","created_at":"2026-07-05T08:22:21.567349+00:00"},{"alias_kind":"pith_short_12","alias_value":"FCGTOC574WSN","created_at":"2026-07-05T08:22:21.567349+00:00"},{"alias_kind":"pith_short_16","alias_value":"FCGTOC574WSNQO7A","created_at":"2026-07-05T08:22:21.567349+00:00"},{"alias_kind":"pith_short_8","alias_value":"FCGTOC57","created_at":"2026-07-05T08:22:21.567349+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.28684","citing_title":"A Neuroimaging Simulation Framework for Developing and Evaluating Causal AI","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2506.14399","citing_title":"Factored Classifier-Free Guidance","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2509.20846","citing_title":"Causal Time Series Generation via Diffusion Models","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FCGTOC574WSNQO7A6MFY7PLTTB","json":"https://pith.science/pith/FCGTOC574WSNQO7A6MFY7PLTTB.json","graph_json":"https://pith.science/api/pith-number/FCGTOC574WSNQO7A6MFY7PLTTB/graph.json","events_json":"https://pith.science/api/pith-number/FCGTOC574WSNQO7A6MFY7PLTTB/events.json","paper":"https://pith.science/paper/FCGTOC57"},"agent_actions":{"view_html":"https://pith.science/pith/FCGTOC574WSNQO7A6MFY7PLTTB","download_json":"https://pith.science/pith/FCGTOC574WSNQO7A6MFY7PLTTB.json","view_paper":"https://pith.science/paper/FCGTOC57","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.11011&json=true","fetch_graph":"https://pith.science/api/pith-number/FCGTOC574WSNQO7A6MFY7PLTTB/graph.json","fetch_events":"https://pith.science/api/pith-number/FCGTOC574WSNQO7A6MFY7PLTTB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FCGTOC574WSNQO7A6MFY7PLTTB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FCGTOC574WSNQO7A6MFY7PLTTB/action/storage_attestation","attest_author":"https://pith.science/pith/FCGTOC574WSNQO7A6MFY7PLTTB/action/author_attestation","sign_citation":"https://pith.science/pith/FCGTOC574WSNQO7A6MFY7PLTTB/action/citation_signature","submit_replication":"https://pith.science/pith/FCGTOC574WSNQO7A6MFY7PLTTB/action/replication_record"}},"created_at":"2026-07-05T08:22:21.567349+00:00","updated_at":"2026-07-05T08:22:21.567349+00:00"}